The Model Index
Up to four models

DeepSeek-V4-Pro vs Qwen3.8-Flash-Next

On the index (GPT-4 = 100), DeepSeek-V4-Pro scores 163 and Qwen3.8-Flash-Next 162. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to DeepSeek-V4-Pro
Presets
DeepSeek-V4-Pro
163147–178
WeightsOpen
ReleasedAug 2026
Price in / out$0.11 / $4.44
Context1.05M
Core tests taken6 of 9
Qwen3.8-Flash-Next
162131–193
WeightsOpen
ReleasedAug 2026
Price in / out–
Context–
Core tests taken0 of 9

DeepSeek-V4-Pro and Qwen3.8-Flash-Next are too close to call (1 point apart, within the uncertainty).

Test by testthird-party results

DeepSeek-V4-ProQwen3.8-Flash-Next
0%25%50%75%100%REASONING & KNOWLEDGELiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningMATHSLiveBench MathematicsLiveBench MathematicsCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench Coding
Every result as a table
TestDeepSeek-V4-ProQwen3.8-Flash-Next
Reasoning & knowledge
LiveBench Data Analysis79.2%74.2%
LiveBench IF67.7%77.1%
LiveBench Language82.1%74.6%
LiveBench Reasoning85.8%87.4%
Maths
LiveBench Mathematics95.1%85.8%
Coding
LiveBench Agentic Coding54.9%61.6%
LiveBench Coding77.2%72.5%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG